Skip to content

GitLab

Switch branch/tag
  1. 10 May, 2023 2 commits
  3. 29 Apr, 2023 1 commit
  5. 28 Apr, 2023 1 commit
    • Yuekai Zhang's avatar
      Add cuctc decoder (#3096) · 0a1801ed
      Yuekai Zhang authored 
      Summary:
This PR implements a CUDA based ctc prefix beam search decoder.

Attach serveral benchmark results using V100 below:
|decoder type| model |datasets       | decoding time (secs)| beam size | batch size | model unit | subsampling times | vocab size |
|--------------|---------|------|-----------------|------------|-------------|------------|-----------------------|------------|
| cuctc |  conformer nemo    |dev clean        |7.68s | 8           |  32       | bpe         |    4  | 1000|
| cuctc |  conformer nemo   |dev clean  (sort by length)      |1.6s | 8           |  32       | bpe         |    4  | 1000|
| cuctc |  wav2vec2.0 torchaudio |dev clean                                |22s | 10           |  1       | char         |    2  | 29|
| cuctc |   conformer espnet   |aishell1 test                             | 5s | 10           |  24       | char         |    4  | 4233|

Note:
1.  The design is to parallel computation through batch and vocab axis, for loop the frames axis. So it's more friendly with smaller sequence lengths, larger vocab size comparing with CPU implementations.
2. WER is the same as CPU implementations. However, it can't decode with LM now.

Resolves: https://github.com/pytorch/audio/issues/2957.

Pull Request resolved: https://github.com/pytorch/audio/pull/3096

Reviewed By: nateanl

Differential Revision: D44709397

Pulled By: mthrok

fbshipit-source-id: 3078c54a2b44dc00eb4a81b4c657487eeff8c155
      0a1801ed
  7. 11 Apr, 2023 1 commit
  9. 10 Apr, 2023 1 commit
  11. 01 Apr, 2023 1 commit
    • moto's avatar
      Add AudioEffector (#3163) · a4036248
      moto authored 
      Summary:
This commit adds a new feature AudioEffector, which can be used to
apply various effects and codecs to waveforms in Tensor.

Under the hood it uses StreamWriter and StreamReader to apply
filters and encode/decode.

This is going to replace the deprecated `apply_codec` and
`apply_sox_effect_tensor` functions.

It can also perform online, chunk-by-chunk filtering.

Tutorial to follow.

closes https://github.com/pytorch/audio/issues/3161

Pull Request resolved: https://github.com/pytorch/audio/pull/3163

Reviewed By: hwangjeff

Differential Revision: D44576660

Pulled By: mthrok

fbshipit-source-id: 2c5cc87082ab431315d29d56d6ac9efaf4cf7aeb
      a4036248
  13. 27 Mar, 2023 1 commit
    • hwangjeff's avatar
      Revise encoder config arg and docstrings (#3203) · b1de9f1a
      hwangjeff authored 
      Summary:
For `StreamWriter`,
* Renames arg `config` to codec_config`.
* Renames struct `EncodingConfig` and dataclass `EncodeConfig` to `CodecConfig`.
* Adds docstrings for arg codec_config`.
* Updates `chunk` to `frames` in `write_*_chunk` methods.

Pull Request resolved: https://github.com/pytorch/audio/pull/3203

Reviewed By: mthrok

Differential Revision: D44350153

Pulled By: hwangjeff

fbshipit-source-id: 1b940b1366a43ec0565c362bfcbf62744088b343
      b1de9f1a
  15. 23 Mar, 2023 2 commits
  17. 21 Mar, 2023 2 commits
  19. 17 Mar, 2023 2 commits
  21. 15 Mar, 2023 1 commit
    • Carl Parker's avatar
      Enhance UX on TorchAudio pages to improve awareness of doc versioning (#3167) · 92f2ea89
      Carl Parker authored 
      Summary:
- Boldface the version-selection UX and increase size by three percent.
- Add text to breadcrumbs to indicate version and stability.
- New `breadcrumbs.html` in `_templates` overrides Sphinx version.

I create a new variable in `conf.py`, **version_stable**, which has the version number for the most-recent stable release. I define this variable in the **html_context** dictionary so that it is visible to the templates.

I use this approach because I was not able to find any other way of discerning the current stable release during the build. Note that the `versions.html` file--which identifies the current stable release--appears to be available only in the **gh-pages** branch and so it is not available at build time.

However, this means that someone will need to update `conf.py` whenever the current stable release changes.

Pull Request resolved: https://github.com/pytorch/audio/pull/3167

Reviewed By: mthrok

Differential Revision: D44112224

Pulled By: carljparker

fbshipit-source-id: e76f5cb6734a784d161342964459577aa9b64cac
      92f2ea89
  23. 14 Mar, 2023 2 commits
  25. 08 Mar, 2023 1 commit
    • moto's avatar
      Include format information after filter (#3155) · 146195d8
      moto authored 
      Summary:
This commit adds fields to OutputStream, which shows the result
of fitlers, such as width and height after filtering.

Before

```
OutputStream(
    source_index=0,
    filter_description='fps=3,scale=width=320:height=320,format=pix_fmts=gray')
```

After

```
OutputVideoStream(
    source_index=0,
    filter_description='fps=3,scale=width=320:height=320,format=pix_fmts=gray',
    media_type='video',
    format='gray',
    width=320,
    height=320,
    frame_rate=3.0)
```

Pull Request resolved: https://github.com/pytorch/audio/pull/3155

Reviewed By: nateanl

Differential Revision: D43882399

Pulled By: mthrok

fbshipit-source-id: 620676b1a06f293fdd56de8203a11120f228fa2d
      146195d8
  27. 02 Mar, 2023 1 commit
  29. 27 Feb, 2023 1 commit
  31. 24 Feb, 2023 2 commits
  33. 22 Feb, 2023 1 commit
  35. 15 Feb, 2023 1 commit
  37. 14 Feb, 2023 2 commits
  39. 11 Feb, 2023 1 commit
  41. 09 Feb, 2023 1 commit
  43. 07 Feb, 2023 1 commit
  45. 01 Feb, 2023 1 commit
  47. 27 Jan, 2023 1 commit
  49. 26 Jan, 2023 1 commit
  51. 24 Jan, 2023 1 commit
  53. 23 Jan, 2023 1 commit
  55. 22 Jan, 2023 1 commit
    • moto's avatar
      Make StreamReader return PTS (#2975) · 0dd59e0d
      moto authored 
      Summary:
This commit makes `StreamReader` report PTS (presentation time stamp) of the returned chunk as well.

Example

```python
from torchaudio.io import StreamReader

s = StreamReader(...)
s.add_video_stream(...)
for (video_chunk, ) in s.stream():
    # video_chunk is Torch tensor type but has extra attribute of PTS
    print(video_chunk.pts)  # reports the PTS of the first frame of the video chunk.
```

For the backward compatibility, we introduce a `_ChunkTensor`, that is a composition
of Tensor and metadata, but works like a normal tensor in PyTorch operations.

The implementation of `_ChunkTensor` is based on [TrivialTensorViaComposition](https://github.com/albanD/subclass_zoo/blob/0eeb1d68fb59879029c610bc407f2997ae43ba0a/trivial_tensors.py#L83).

It was also suggested to attach metadata directly to Tensor object,
but the possibility to have the collision on torchaudio's metadata and new attributes introduced in
PyTorch cannot be ignored, so we use Tensor subclass implementation.

If any unexpected issue arise from metadata attribute name collision, client code can
fetch the bare Tensor and continue.

Pull Request resolved: https://github.com/pytorch/audio/pull/2975

Reviewed By: hwangjeff

Differential Revision: D42526945

Pulled By: mthrok

fbshipit-source-id: b4e9422e914ff328421b975120460f3001268f35
      0dd59e0d
  57. 15 Jan, 2023 1 commit
    • Zhaoheng Ni's avatar
      Add pre-trained pipelines for XLS-R models (#2978) · 9b7b64e4
      Zhaoheng Ni authored 
      Summary:
The PR adds three `Wav2Vec2Bundle ` pipeline objects for XLS-R models:
- WAV2VEC2_XLSR_300M
- WAV2VEC2_XLSR_1B
- WAV2VEC2_XLSR_2B

All three models use layer normalization in the feature extraction layers, hence `_normalize_waveform` is set to `True`.

Pull Request resolved: https://github.com/pytorch/audio/pull/2978

Reviewed By: hwangjeff

Differential Revision: D42501491

Pulled By: nateanl

fbshipit-source-id: 2429ec880cc14798034843381e458e1b4664dac3
      9b7b64e4
  59. 13 Jan, 2023 1 commit
  61. 06 Jan, 2023 1 commit
  63. 05 Jan, 2023 2 commits